JAIST Repository >
School of Information Science >
Conference Papers >
Conference Papers >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/16248

Title: Multitask Learning and Multistage Fusion for Dimensional Audiovisual Emotion Recognition
Authors: Atmaja, Bagus Tris
Akagi, Masato
Keywords: multitask learning
multistage fusion
audiovisual emotion recognition
dimensional emotion
Issue Date: 2020-05
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Magazine name: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Start page: 4482
End page: 4486
DOI: 10.1109/ICASSP40776.2020.9052916
Abstract: Due to its ability to accurately predict emotional state using multimodal features, audiovisual emotion recognition has recently gained more interest from researchers. This paper proposes two methods to predict emotional attributes from audio and visual data using a multitask learning and a fusion strategy. First, multitask learning is employed by adjusting three parameters for each attribute to improve recognition rate. Second, a multistage fusion is proposed to combine results from various modalities final prediction. Our approach used multitask learning, employed at unimodal and early fusion methods, shows improvement over single-task learning with an average CCC score of 0.431 compared to 0.297. Multistage method, employed at the late fusion approach, significantly improved the agreement score between true and predicted values on the development set of data (from [0.537, 0.565, 0.083] to [0.68, 0.656, 0.443]) for arousal, valence, and liking.
Rights: This is the author's version of the work. Copyright (C) 2020 IEEE. 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, pp.4482-4486. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
URI: http://hdl.handle.net/10119/16248
Material Type: author
Appears in Collections:b11-1. 会議発表論文・発表資料 (Conference Papers)

Files in This Item:

File Description SizeFormat
ICASSP2020_Bagus.pdf196KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.


Contact : Library Information Section, Japan Advanced Institute of Science and Technology